Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A production-oriented demo of a decision-map architecture where Playwright performs deterministic browser actions and hard assertions, while TypeSafe Jev answers narrow typed semantic questions over compact accessibility snapshots. Aimed at teams building semantic test automation without generative LLMs in the regression path.
How it uses Jev
Jev answers narrow typed semantic questions (noul, choice, score) against compact accessibility snapshots; Playwright keeps deterministic actions and hard assertions. The README does not specify which exact decisions Jev makes or how results are wired into code.
Primitives:choicescorenoul
Technique worth stealing
Keep generative LLMs out of the regression path: use typed questions over compact accessibility snapshots for semantics, Playwright for determinism.
Try it
npm install; npx playwright install chromium; optionally export TYPESAFE_API_KEY; then npx playwright test.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.92
- Shows a System One patternFound in material0.86
- Describes handling uncertaintyFound in material0.71
- Reports measured numbersunclear0.44
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalunclear0.52
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale0.94 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
Design patterns
No pattern scored above the reporting threshold.
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 3 Nov 2026.